Comparative Study of Various Artificial Intelligence Techniques to Predict Software Quality

Software quality prediction models are used to identify software modules that may cause potential quality problems. These models are based on various metrics available during the early stages of software development life cycle like product size, software complexity, coupling and cohesion. In this su...

Full description

Saved in:
Bibliographic Details
Main Authors: Khan, M.J., Shamail, S., Awais, M.M., Hussain, T.
Format: Conference Proceeding
Language:English
Subjects:
Artificial intelligence
Bayesian methods
Fuzzy logic
Neural networks
Predictive models
Programming
Software algorithms
Software quality
Support vector machine classification
Support vector machines
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Software quality prediction models are used to identify software modules that may cause potential quality problems. These models are based on various metrics available during the early stages of software development life cycle like product size, software complexity, coupling and cohesion. In this survey paper, we have compared and discussed some software quality prediction approaches based on Bayesian belief network, neural networks, fuzzy logic, support vector machine, expectation maximum likelihood algorithm and case-based reasoning. This study gives better comparative insight about these approaches, and helps to select an approach based on available resources and desired level of quality.
DOI:10.1109/INMIC.2006.358157